Physics-guided deep learning for damage detection in CFRP composite structures

Abstract

Structural health monitoring of carbon fiber reinforced plastics composite structures based on deep learning usually builds on black box models for damage detection. However, the lack of physics knowledge limits its application into real-world problems where structural property or environmental condition varies. To overcome this limitation, we propose a physics-guided deep learning framework to integrate physics into data-driven models. This physics-guided convolutional neural network leverages structural degradation trend and physical consistency by combining the output of the physical model with the observed feature in a hybrid model. This hybrid model uses an additional branch to observe the information of stiffness degradation, which is the input into the physical model to describe the damage growth in structures by establishing a relationship with the power spectral density change in the guided wave signals. Additionally, the physics-based loss function is designed as part of the learning objective to ensure the model outputs satisfy the existing physics and maintain physical consistency. Experiment results show that our method demonstrates great generalizability that by training on data of only one particular CFRP composite structure, the PGCNN model can expand its great performance on all other CFRP layups in the NASA-published CFRP Dataset with over 90% accuracy.